Related papers: Routing Memento Requests Using Binary Classifiers
Retrieval-Augmented Generation (RAG) significantly improves the performance of Large Language Models (LLMs) on knowledge-intensive tasks. However, varying response quality across LLMs under RAG necessitates intelligent routing mechanisms,…
We focus on two research issues in entity search: scoring a document or snippet that potentially supports a candidate entity, and aggregating scores from different snippets into an entity score. Proximity scoring has been studied in IR…
Dynamic web applications such as mashups need efficient access to web data that is only accessible via entity search engines (e.g. product or publication search engines). However, most current mashup systems and applications only support…
LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs, and increasing compute cost and GPU memory overhead. To address this issue, we propose MemSearcher, an agent framework…
Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ranking. To overcome this challenge, this paper presents BECR…
This paper presents a hybrid machine learning method of classifying residential requests in natural language to responsible departments that provide timely responses back to residents under the vision of digital government services in smart…
Abstractive summarization aims to generate a shorter version of the document covering all the salient points in a compact and coherent fashion. On the other hand, query-based summarization highlights those points that are relevant in the…
Text extraction from web pages has many applications, including web crawling optimization and document clustering. Though much has been written about the acquisition of content from live web pages, content acquisition of archived web pages,…
Crucial performance metrics of a caching algorithm include its ability to quickly and accurately learn a popularity distribution of requests. However, a majority of work on analytical performance analysis focuses on hit probability after an…
Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. To obtain high efficiency,…
Small base stations (SBs) of fifth-generation (5G) cellular networks are envisioned to have storage devices to locally serve requests for reusable and popular contents by \emph{caching} them at the edge of the network, close to the end…
We study black-box attacks on machine learning classifiers where each query to the model incurs some cost or risk of detection to the adversary. We focus explicitly on minimizing the number of queries as a major objective. Specifically, we…
Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing…
Web application performance is heavily reliant on the hit rate of memory-based caches. Current DRAM-based web caches statically partition their memory across multiple applications sharing the cache. This causes under utilization of memory…
Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies. However, existing methods struggle especially when several incremental steps are performed.…
Comprehensively retrieving diverse documents is crucial to address queries that admit a wide range of valid answers. We introduce retrieve-verify-retrieve (RVR), a multi-round retrieval framework designed to maximize answer coverage.…
Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language models (LMs) is slow and difficult to scale due to…
Neural retrieval models excel in Web search, but their training requires substantial amounts of labeled query-document pairs, which are costly to obtain. With the widespread availability of Web document collections like ClueWeb22, synthetic…
We propose a quantum repeater protocol and architecture that mitigates decoherence of the entangled states by optimizing the quantum memory buffer time. The protocol maximizes the rate of distillable entanglement in the average accessed…
We introduce the \emph{Private Contiguous-Block Retrieval (PCBR)} problem, where a user retrieves a block of $D$ messages with contiguous indices from $K$ replicated messages stored across $N$ non-colluding servers, while hiding the…